{"id":"https://openalex.org/W7131215620","doi":"https://doi.org/10.1186/s40537-026-01365-0","title":"Comprehensive representation of health-related phenotypes in one million dogs using topic modelling of electronic health records","display_name":"Comprehensive representation of health-related phenotypes in one million dogs using topic modelling of electronic health records","publication_year":2026,"publication_date":"2026-02-24","ids":{"openalex":"https://openalex.org/W7131215620","doi":"https://doi.org/10.1186/s40537-026-01365-0","pmid":"https://pubmed.ncbi.nlm.nih.gov/41924019"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-026-01365-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-026-01365-0","pdf_url":null,"source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s40537-026-01365-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011927604","display_name":"Peter\u2010John M. Noble","orcid":"https://orcid.org/0000-0002-2275-2014"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Peter-John M\u00e4ntyl\u00e4 Noble","raw_affiliation_strings":["Department of Small Animal Clinical Science, Institute of Veterinary and Ecological Sciences, University of Liverpool, Leahurst Campus, Chester High Road, Neston, CH64 7TE Wirral UK"],"raw_orcid":"https://orcid.org/0000-0002-2275-2014","affiliations":[{"raw_affiliation_string":"Department of Small Animal Clinical Science, Institute of Veterinary and Ecological Sciences, University of Liverpool, Leahurst Campus, Chester High Road, Neston, CH64 7TE Wirral UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007049450","display_name":"Sean Farrell","orcid":"https://orcid.org/0000-0002-1358-4979"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sean Oliver Farrell","raw_affiliation_strings":["Department of Computer Science, Durham University, Upper Mountjoy Campus, Stockton Road, Durham, DH1 3LE UK","School of Medicine, Stanford University, Stanford, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-1358-4979","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Durham University, Upper Mountjoy Campus, Stockton Road, Durham, DH1 3LE UK","institution_ids":["https://openalex.org/I190082696"]},{"raw_affiliation_string":"School of Medicine, Stanford University, Stanford, California, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091886479","display_name":"Noura Al-Moubayed","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Noura Al-Moubayed","raw_affiliation_strings":["Department of Computer Science, Durham University, Upper Mountjoy Campus, Stockton Road, Durham, DH1 3LE UK"],"raw_orcid":"https://orcid.org/0000-0001-8942-355X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Durham University, Upper Mountjoy Campus, Stockton Road, Durham, DH1 3LE UK","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126671576","display_name":"Alan David Radford","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alan David Radford","raw_affiliation_strings":["Department of Infection Biology and Microbiomes, Institute of Veterinary and Ecological Sciences, University of Liverpool, Leahurst Campus, Chester High Road, Neston, CH64 7TE Wirral UK"],"raw_orcid":"https://orcid.org/0000-0002-4590-1334","affiliations":[{"raw_affiliation_string":"Department of Infection Biology and Microbiomes, Institute of Veterinary and Ecological Sciences, University of Liverpool, Leahurst Campus, Chester High Road, Neston, CH64 7TE Wirral UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011927604"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":20.7337,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98289305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"13","issue":"1","first_page":"50","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12492","display_name":"Zoonotic diseases and public health","score":0.3375000059604645,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12492","display_name":"Zoonotic diseases and public health","score":0.3375000059604645,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11214","display_name":"Human-Animal Interaction Studies","score":0.13259999454021454,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.08470000326633453,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5336999893188477},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5031999945640564},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.4986000061035156},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4634000062942505},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.4537000060081482},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.4413999915122986},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.36250001192092896},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3212999999523163},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.31459999084472656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652400016784668},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5336999893188477},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.4413999915122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3758000135421753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3125},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C3020646490","wikidata":"https://www.wikidata.org/wiki/Q25203551","display_name":"Clinical phenotype","level":4,"score":0.3034000098705292},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C2776482104","wikidata":"https://www.wikidata.org/wiki/Q38829","display_name":"Breed","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.26489999890327454},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s40537-026-01365-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-026-01365-0","pdf_url":null,"source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmid:41924019","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41924019","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of big data","raw_type":null},{"id":"pmh:oai:durham-repository.worktribe.com:5191407","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/5191407","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:pubmedcentral.nih.gov:13035608","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13035608/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Big Data","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s40537-026-01365-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-026-01365-0","pdf_url":null,"source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331281","display_name":"Dogs Trust","ror":"https://ror.org/03nfnrd41"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1970786358","https://openalex.org/W2048039545","https://openalex.org/W2116810060","https://openalex.org/W2161537292","https://openalex.org/W2163278718","https://openalex.org/W2172721573","https://openalex.org/W2282821441","https://openalex.org/W2601243251","https://openalex.org/W2611933891","https://openalex.org/W2621383949","https://openalex.org/W2733224981","https://openalex.org/W2803031018","https://openalex.org/W2883730939","https://openalex.org/W2889326414","https://openalex.org/W2891971692","https://openalex.org/W2897056441","https://openalex.org/W2906584200","https://openalex.org/W2908300865","https://openalex.org/W2963341956","https://openalex.org/W2991157178","https://openalex.org/W3005650752","https://openalex.org/W3032050396","https://openalex.org/W3034701499","https://openalex.org/W3037263452","https://openalex.org/W3120606777","https://openalex.org/W3158319314","https://openalex.org/W3200824497","https://openalex.org/W4200348135","https://openalex.org/W4225426732","https://openalex.org/W4304113609","https://openalex.org/W4378349316","https://openalex.org/W4378905538","https://openalex.org/W4385581086","https://openalex.org/W4387845654","https://openalex.org/W4390858558","https://openalex.org/W4391101431","https://openalex.org/W4398175702","https://openalex.org/W4399859641","https://openalex.org/W4404538651","https://openalex.org/W4405334792"],"related_works":[],"abstract_inverted_index":{"Historically,":[0],"veterinary":[1,122],"studies":[2,17,77],"screening":[3,61],"for":[4,62],"breed,":[5],"age":[6],"and":[7,142,159,174,198],"sex":[8],"predisposition":[9],"to":[10,39,147,155],"disease":[11,58,63,170],"have":[12],"relied":[13],"on":[14,134],"collating":[15],"small-scale":[16],"of":[18,23,45,56,73,89,93,111,115,169,182,189,193,202,206],"clinical":[19,46,116,184],"datasets.":[20],"The":[21,214],"availability":[22],"larger":[24],"datasets":[25],"through":[26],"groups":[27],"such":[28,151],"as":[29,152,163,165],"the":[30,54,71,90,94,125,179,187,196,199],"Small":[31],"Animal":[32],"Veterinary":[33],"Surveillance":[34],"Network":[35],"(SAVSNET)":[36],"promise":[37],"access":[38],"information":[40,59],"regarding":[41],"a":[42,67,86,109,112,130,190],"wide":[43],"range":[44,192],"presentations":[47],"at":[48,96,221],"scale,":[49],"however,":[50],"methodological":[51],"limitations":[52],"surrounding":[53],"extraction":[55],"specific":[57],"or":[60,209],"predispositions":[64,154],"result":[65],"in":[66,70],"substantial":[68],"reduction":[69],"number":[72],"animals":[74],"studied.":[75],"These":[76],"often":[78],"address":[79],"very":[80],"focused":[81],"hypotheses":[82],"-":[83],"only":[84],"leveraging":[85],"small":[87],"fraction":[88],"intrinsic":[91],"value":[92],"data":[95],"any":[97],"one":[98],"time.":[99],"Here,":[100],"we":[101],"implemented":[102],"an":[103],"unsupervised":[104],"machine":[105],"learning":[106],"methodology,":[107],"creating":[108],"representation":[110],"large":[113,183],"volume":[114],"notes":[117],"collected":[118],"by":[119],"SAVSNET":[120],"from":[121],"practices":[123],"across":[124],"UK.":[126],"We":[127],"utilise":[128],"BERTopic,":[129],"topic-modelling":[131],"tool":[132],"based":[133],"Bidirectional":[135],"Encoder":[136],"Representations":[137],"using":[138],"Transformers":[139],"(BERT)":[140],"architecture,":[141],"show":[143],"it":[144],"is":[145],"able":[146],"surface":[148],"known":[149],"phenotypes,":[150],"breed":[153],"hypoadrenocorticism,":[156],"diabetes":[157],"mellitus":[158],"mitral":[160],"valve":[161],"disease,":[162],"well":[164],"potential":[166],"novel":[167],"patterns":[168],"phenotypes.":[171],"This":[172],"scalable":[173],"granular":[175],"modelling":[176],"technique":[177],"facilitates":[178],"rapid":[180],"interrogation":[181],"datasets,":[185],"enabling":[186],"identification":[188],"broad":[191],"phenotypes":[194],"within":[195],"population":[197],"early":[200],"detection":[201],"temporal":[203],"changes":[204],"indicative":[205],"emerging":[207],"infectious":[208],"environmental":[210],"diseases.":[211],"Supplementary":[212],"Information:":[213],"online":[215],"version":[216],"contains":[217],"supplementary":[218],"material":[219],"available":[220],"10.1186/s40537-026-01365-0.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-25T00:00:00"}